Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .UseText
    -0.07
     دادن
    -0.07
     Schul
    -0.06
     Francois
    -0.06
    _workers
    -0.06
     graded
    -0.06
    .Debugger
    -0.06
    .IsMatch
    -0.06
    ープ
    -0.06
     اجتماع
    -0.06
    POSITIVE LOGITS
     continual
    0.07
     teach
    0.07
     CGI
    0.06
    urface
    0.06
    ()},↵
    0.06
    warm
    0.06
    inue
    0.06
     troubled
    0.06
     charging
    0.06
    _DEVICE
    0.06
    Act Density 0.006%

    No Known Activations